Are there any other models being distilled? The Dreamshaper one is, uh, very unsafe for work.
@fofrai
-
Does Latent Consistency Model Support Image-to-Image Workflows?
By
–
Does the latent consistency model also support img2img workflows?
-
Latent Consistency Model enables ultra-fast image generation on Replicate
By
–
Super fast images with the latent consistency model now on Replicate: https://
replicate.com/cjwbw/latent-c
onsistency-model
… 4x 512×512 images, 4 steps in 3.3 seconds https://
replicate.com/p/s6kixk3bgxsh
2phwgclpdap66e
… -
Image Quality Analysis: Softness and Grain Patterns in AI Generation
By
–
Some of the softness I've seen is similar to softness I'd expect in my own photos. But I agree, there is some grainy pattern there, and more obvious on non-photo subjects I think.
-
AI Photography Styles: Best Practices and Applications
By
–
They seem to work best on photography styles.
-
Midjourney’s 4x upscales deliver impressive image enhancement results
By
–
Midjourney’s 4x upscales are very impressive
-
AI-Generated Music Video Using Show-1 and MusicGen
By
–
By which I mean, I used Show-1 text-to-video combined with the Slipknot MusicGen fine-tune to make a music video.
-
MusicGen Fine-Tune Delivers Impressive Slipknot-Style Music Results
By
–
This MusicGen fine-tune goes hard.https://t.co/QBNQeFI26J
— fofr (@fofrAI) 18 octobre 2023
The end, dang! 🤘 pic.twitter.com/eJDYlEbGiJThis MusicGen fine-tune goes hard. https://
replicate.com/fofr/musicgen-
slipknot
… The end, dang! -
LLaMA-13B Model Classifies Text-to-Image Prompts for Safety
By
–
To go alongside sdxl-emoji I also trained a llama-13b fine-tune to classify text to image prompts as safe (0) or toxic (10). That model is also approaching 1M runs: https://
replicate.com/fofr/prompt-cl
assifier
… Trained on all the toxic prompts people tried after hitting #1 on Hacker News.